TEST #4096 RESULTS
08/28/2026 - 12:47 PM
ACCELERATOR
MODEL
2.1
tokens/s
generation
65.11
sec
time to first token
21
tokens/s
prompt
9
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
AMD Ryzen 7 5700G with Radeon Graphics (znver3)
RAM
45.9GB
OS
Linux
Kernel Release
6.12.105+deb13-amd64
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64; #1 SMP PREEMPT_DYNAMIC Debian 6.12.105-1 (2026-08-24)
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
20
tokens/s
2.1
tokens/s
52.70
sec
pp4096+tg256
19
tokens/s
1.9
tokens/s
212.42
sec
pp2048+tg256
22
tokens/s
2.2
tokens/s
95.94
sec
pp2048+tg768
20
tokens/s
2.1
tokens/s
100.56
sec
pp1024+tg1024
22
tokens/s
2.2
tokens/s
46.00
sec
pp1280+tg3072
23
tokens/s
1.7
tokens/s
57.13
sec
pp384+tg1152
23
tokens/s
2.3
tokens/s
16.83
sec
pp64+tg1024
25
tokens/s
2.4
tokens/s
3.04
sec
pp16+tg1536
17
tokens/s
2.3
tokens/s
1.34
sec